jonasengelmann's repositories
pydantic-cidoc-crm
A Python implementation of Cidoc-CRM using pydantic and rdflib.
waybackmachine_linkarchiver
Easily push links found in documents and replace them with their archived version.
worldcat-reconciliation-service
Worldcat.org reconciliation service for OpenRefine.
crossref-reconciliation-service
Crossref.org reconciliation service for OpenRefine.
erinnerungsluecken-im-nsu-untersuchungsausschuss
A semantic matcher is trained using BERT to identify all situations in which witnesses expresses their inability to remember.
forced_alignment_preparation_tools
A small collection of Python3 scripts that help prepare language data for forced alignment.
go-pmtiles
Single-file executable tool for working with PMTiles archives
kafka_tagebuch_bot
A gpt-2 fine-tuned model that generates german diary entries in the style of Franz Kafka (sort of)
NYTdiff
Code for the twitter bot nyt_diff & lesoir_diff
topic_modeling_example
An example of topic modeling using Latent Dirichlet Allocation (LDA) and testing various visualizations and evaluations methods. As testcorpus articles from the online newspaper zeit.de are used.
openseadragon
An open-source, web-based viewer for zoomable images, implemented in pure JavaScript.